© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2958
    Prev
    Next
    INDEX
    Explanations

    say rel

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    夏
    -19.00
     demos
    -18.00
     ctx
    -17.25
    (ctx
    -16.75
    注
    -16.75
     annotation
    -16.25
    _annotation
    -16.13
     annotations
    -16.00
     capture
    -15.81
    Tube
    -15.56
    POSITIVE LOGITS
     rel
    96.00
    Rel
    86.50
     Rel
    86.50
    (rel
    85.00
    rel
    81.50
    -rel
    79.00
    .rel
    76.00
    _rel
    72.50
     REL
    69.50
    REL
    66.00
    Activations Density 0.249%

    No Known Activations